DBL: Dual-Level balanced learning for long-Tailed classification

Real-world data are typically long-tailed, causing neural networks to over-fit head classes and underperform on rare tails. We propose Dual-Level Balanced Learning (DBL), an efficient training framework that balances gradients at both the class and instance levels. DBL combines Class-aware Balancing (CB), which corrects class-level imbalance by re-weighting gradients according to prediction bias; Instance-aware Balancing (IB), which alleviates instance-level imbalance by emphasising the learning of hard examples; and a lightweight Cross-Level Collaboration (CC) scheme that harmonises the two losses. By jointly addressing class- and instance-level imbalance, DBL delivers consistent gains across all classes and most individual samples. Extensive experiments on CIFAR10/100-LT, ImageNet-LT, Places-LT, and iNaturalist18 show that DBL sets new state-of-the-art accuracy on all five benchmarks, confirming its robustness to severe long-tailed distributions.